OUR WORK

Black and white halftone portrait of a man with short hair, wearing a collared shirt, with colored hexagons in the background.

25 YEARS OF PARTNERSHIP TAX INNOVATION

For more than 25 years, our solutions have served the largest public accounting firms and US partnerships.

Email Us
Diagram showing AI symbol connected to a red honeycomb pattern forming a snowflake shape.

2026

TIERS AI next-generation solution.

Learn more
Black and white photo of a woman working on a laptop, surrounded by digital graphics and hexagonal shapes in red, yellow, gray, and black.

2024

Sale of Document Intelligence system and related inventions to Big 4 firm. Widespread rollout in year one.

Learn more
A black and white digital illustration of a woman with short hair, wearing a collared shirt, holding a pen to her chin, with a thoughtful expression. There are geometric shapes and hexagons in red, yellow, and gray around her in the background.

2020

Sale of cloud-first partnership tax compliance system to an international firm. Nine-figure ROI in year one.

Learn more
Illustration of a central red hexagon pattern with white, gray, beige, and yellow hexagons radiating outward, connected by dashed lines.

2018

Experimental machine learning system to automate the extraction of structured data from K-1s and footnotes eliminated 30,000 labor hours in the first busy season of use.

Learn more

2017

Development of a deep partnership modeling platform for Big 4 National Office M&A practice. Used to model and propose Up-C conversions of the largest publicly traded US PE entities.

Learn more
Man working on multiple computer monitors with code, surrounded by coffee cups and tech accessories in a black-and-white office setting, with abstract chemical structure graphics in the background.

2013

Sale of breakthrough Sub K tax allocation engine and related inventions to Big 4 firm. Over next three years, developed it into the market-leading platform.

2011

Developed in-memory analysis and ubiquitous parallel processing techniques

Learn more
A seed from a maple tree.

2001

Pioneered early software solutions for partnership tax, including 704(b), 704(c), and 752 allocation logic.

2024

The Development of Partnership Document Intelligence

Beginning in 2021, using emerging AI and ML capabilities, we developed a new system for comprehension of K-1s, K-3s, footnotes, and other associated tax documents.

In 2024 a Big 4 accounting firm entered an agreement to purchase this system and related inventions.

Integrating multiple AI strategies, this system understands and extracts data from complex documents with unprecedented speed and accuracy.

Document Intelligence comprehends hundreds of semantic concepts and data types, including but not limited to:

  • The face of the K-1, with self-programming to account for document template variations

  • Overflow statements and other form face-related detail footnotes

  • Other critical footnotes including DRD, ECI, UBTI, FDAP, PFIC, Installment Sales, Passive Activity, QBI / 199A, 926, 8621, 8865, and 8886

  • State-source income matrices

  • State K-1s including complex forms such as the CA, NY, and PA K-1s

  • The highly complex K-3 and overflow statements

Read the project brief

2020

CLOUD-FIRST Partnership Tax Compliance System

In 2018, we began development of a new partnership tax compliance system using cloud-first strategies and modern system architecture.

In 2020, it was acquired by an international accounting firm.

By the end of the first year, the firm had enjoyed a nine-figure return on investment.

Key features:

  • GAAP to Tax adjustments, allocations, and tiering for partnerships and tiered organizational structures of any size and complexity

  • Primary calculation pipeline for federal, state, and international tax reporting

  • Secondary calculation pipelines for complex Section 704(c) allocations found in real estate partnerships and hedge funds

  • Rapid calculation turnaround for even the largest partnership structures

  • Real-time, in-memory, self-service analytics and reporting functions

  • Inputs and outputs exportable in XLSX and compressed CSV formats

  • Simple integration with Excel, Alteryx, Power BI, and other end-user tools

  • Direct generation of high-quality K-1s, footnotes, K-3s, and K-2

  • Systems integration with widely used tax return filing systems such as GoSystem and CCH

  • Append-only data model with full revision history, tracing capabilities, and the ability to reverse all data changes

  • Instantaneous copying of datasets, with copies made from any point in their revision history

  • Configurable data ingestion and transformation functions for client data sources such as trial balances, balance sheets, and income statements

Automated Extraction of Structured Data from Tax Documents

From 2018 to 2020, we developed several machine learning and heuristic AI-based applications that extract structured data from tax forms and complex footnotes.

These projects succeeded before the advent of modern Large Language Models and Generative AI.

A difficult area in which we made significant progress was the classification and extraction of data from complex footnotes that trigger reporting requirements (e.g., forms 926, 8865, 8886, and 8621).

By 2020, these systems were trained to recognize and extract data from 44 distinct classes of footnote.

The core libraries united open-source software, closed-source commercial software, and custom developed software to produce a unified and royalty-free system for extraction of data from tax documents.

Examples of deployed applications include:

  • A fund-of-funds focused system for ingestion and aggregation of K-1s, overflow schedules, and footnotes. Source documents of varied quality, ranging from high quality searchable PDFs to low quality scanned images. Deployed for use both by line of business staff and a global delivery center. Eliminated 30,000 labor hours in the first year of use.

  • A private-equity focused system to ingest, review, and enhance K-1s in scenarios where the funds receive K-1s from hundreds or thousands of underlying entities.

  • A system for ingestion and general-purpose query of field data from over 2,000 form types (inclusive of variations).

2018

2017

PARTNERSHIP MODELING PLATFORM

Three-year-long development of a deeply technical partnership transaction modeling platform in collaboration with a Big 4 National Office M&A practice.

In 2019, the M&A team modeled and proposed the Up-C conversion of a prominent publicly traded entity.

Upon conversion, that entity enjoyed a significant increase in market value. Other partnerships with similar structures followed.

Core functions include:

  • Tracking over time of partners’ varying 704(b) interests, Section 704(c) differences, and capital accounts. Automation of internal accounting relating to transfers of interest and redemptions.

  • Tracking of Section 704(b) book basis and tax basis of partnership property, including depreciable and amortizable property.

  • Section 704(b) revaluations of partnership property.

  • Section 704(c) depreciation and gain/loss allocations under traditional, remedial, and curative methods. Mixed method approaches where 704(c) methods differ by revaluation layer.

  • Section 752 debt analysis and allocations allowing for recollateralization and other changes in debt fact patterns.

  • Calculation of hypothetical liquidations including detailed gain/loss calculations at the asset, layer, and investor level.

  • Section 751(a) gain recharacterization analysis.

  • Section 751(b) gain analysis on distributions that result in deemed sales or exchanges.

  • Section 731 gain analysis on distributions.

  • Section 732 gain analysis on distributions of partnership property.

  • Section 743(b) adjustment calculations, allocation to property, and ongoing recovery, including both two-way and one-way adjustments.

  • Section 734(b) adjustment calculations, allocation to property, and ongoing recovery.

  • Allocation of miscellaneous other 704(b) book and tax items to partners.

Sub K Partnership TIERING AND ALLOCATION ENGINE

In 2011, we began experimenting with novel software designs incorporating in-memory analysis and ubiquitous parallel processing.

This work yielded a new, high-performance system of algorithms to compute US partnership tax allocations pursuant to IRC Subchapter K.

In 2013, a Big 4 accounting firm purchased this partnership allocation engine and portfolio of related inventions.

Our team was then engaged in a successful multi-year project that resulted in a comprehensive, “GAAP to Tax” partnership tax compliance system.

Our contributions include:

  • All federal and state tax calculation logic

  • Design of the system’s tax-domain conceptual model and its overall data model

  • All system middleware connecting the calculation logic and cloud computing processing and data infrastructure

  • End-user workflow for book-to-tax and other key tax processes

  • Federal and state form production functions

  • Footnote production functions, including free-form HTML text formatting and dynamic compilation of user-specified functions

In 2026, this system remains the core of the firm’s partnership tax compliance practice.

2011

Start the Conversation

Our team will follow up to coordinate a brief call tailored to your needs.

Send an email